Navigating the Evolution of Two-dimensional Carbon Nitride Research: Integrating Machine Learning into Conventional Approaches

Abstract

Carbon nitride research has reached a promising point in today's research endeavours with diverse applications including photocatalysis, energy storage, and sensing due to their unique electronic and structural properties. Recent advances in machine learning (ML) have opened new avenues for exploring and optimizing the potential of these materials. This study presents a comprehensive review of the integration of ML techniques in carbon nitride research with an introduction to CN classifications and recent advancements. We discuss the methodologies employed, such as supervised learning, unsupervised learning, and reinforcement learning, in predicting material properties, optimizing synthesis conditions, and enhancing performance metrics. Key findings indicate that ML algorithms can significantly reduce experimental trial-and-error, accelerate discovery processes, and provide deeper insights into the structure-property relationships of carbon nitride. The synergistic effect of combining ML with traditional experimental approaches is highlighted, showcasing studies where ML driven models have successfully predicted novel carbon nitride compositions with enhanced functional properties. Future directions in this field are also proposed, emphasizing the need for high-quality datasets, advanced ML models, and interdisciplinary collaborations to fully realize the potential of carbon nitride materials in next-generation technologies.

References in corpus (25)

• Electric Field Effect in Atomically Thin Carbon Films
• Automatic chemical design using a data-driven continuous representation of molecules
• Crystal Structure Prediction via Particle Swarm Optimization
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• Robust isothermal electric switching of interface magnetization: A route to voltage-controlled spintronics
• Opportunities and Challenges for Machine Learning in Materials Science
• Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials
• Machine Learning the Voltage of Electrode Materials in Metal-ion Batteries
• Nanoporous C3N4, C3N5 and C3N6 nanosheets; Novel strong semiconductors with low thermal conductivities and appealing optical/electronic properties
• Exploring Phononic Properties of Two-Dimensional Materials using Machine Learning Interatomic Potentials
• Prediction of two-dimensional nodal-line semimetal in a carbon nitride covalent network
• Prediction of C7N6 and C9N4: Stable and strong porous carbon-nitride nanosheets with attractive electronic and optical properties
• Exploring thermal expansion of carbon-based nanosheets by machine-learning interatomic potentials
• Exploring the role of electronic structure on photo-catalytic behavior of carbon-nitride polymorphs
• Thermo-mechanical properties of nitrogenated holey graphene (C2N): A comparison of machine-learning-based and classical interatomic potentials
• Accelerating Material Design with the Generative Toolkit for Scientific Discovery
• E(n)-Equivariant Cartesian Tensor Passing Potential
• Strain Engineering of 2D-C3N5 Monolayer and its Application in Overall Water-Splitting: A Hybrid Density Functional Study
• A new 2D auxetic CN2 nanostructure with high energy density and mechanical strength
• Mapping out phase diagrams with generative classifiers
• Metric-driven search for structurally stable inorganic compounds
• Quantum Spin Hall Effect and Su-Schrieffer-Heeger Model Implementation in Novel C3N-based Dumbbell Morphologies
• MATGANIP: Learning to Discover the Structure-Property Relationship in Perovskites with Generative Adversarial Networks
• Rectangular carbon nitrides C4N monolayers with a zigzag buckled structure: Quasi-one-dimensional Dirac nodal lines and topological flat edge states